© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125584
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a company or financial entities involved in regulatory matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     legality
    -0.07
     pháºŃn
    -0.06
     اÙĨتشار
    -0.06
    hrad
    -0.06
    ottes
    -0.06
     sheep
    -0.06
    oding
    -0.06
    eft
    -0.06
     hold
    -0.06
    åĵ
    -0.06
    POSITIVE LOGITS
     {{--<
    0.07
    onic
    0.07
     ÙĪÛĮÚ©ÛĮ
    0.06
    ÙĪÙĤÙĬت
    0.06
    acam
    0.06
    erval
    0.06
    Stub
    0.06
    clare
    0.06
     Dudley
    0.06
    /inet
    0.06
    Activations Density 0.034%

    No Known Activations